© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44232
    Prev
    Next
    INDEX
    Explanations

    real return or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phenomenal
    0.42
     discordant
    0.42
     unimaginable
    0.42
    adopted
    0.42
    incredible
    0.42
     evolutionary
    0.41
    Н
    0.41
    viable
    0.41
     exalted
    0.40
     intractable
    0.39
    POSITIVE LOGITS
     hoặc
    0.49
     లేదా
    0.49
     Strip
    0.45
     alebo
    0.44
    หรือ
    0.43
     ឬ
    0.42
     مشتر
    0.42
    >∕
    0.42
    onto
    0.41
    거나
    0.41
    Activations Density 0.001%

    No Known Activations